Coupler.io

Get data from a Coupler.io data flow run. Query a sample of 5 rows from data table, e.g. SELECT * from data LIMIT 5, and then run the get-schema tool, to better understand the structure. The get-schema tool will return the JSON-encoded schema of the data table. When visualizing the data, do not try to read any files or fetch any URLs, just generate a static page and use the data you get from the tools.

Get the current state of a Coupler.io dataflow by its ID, including its sources and destinations.

Get data table schema from a Coupler.io data flow. Get column names from columnName properties in column definitions. Example: {"columns":[{"key":"Row Updated At.0","label":"Row Updated At","schema":{"type":"string"},"typeOptions":{},"columnName":"col_0"},...]}. Here the columns are col_0 and col_1. If there is any ai_context always take that into account in your response.

Get a skill's full instructions by name. Call this after list-skills returns a matching skill. You must follow the returned procedure to complete the task.

DEPRECATED. Use "list-datasets" instead.

List datasets from Coupler.io dataflows. Use this to discover available datasets, including total number of datasets, optionally filtered by a specific dataflow, and provide insights about their contents.

List available skills — specialized workflows that handle common requests end-to-end. Returns skill names and short descriptions. If a match exists, call get-skill to retrieve the full procedure.

List templates available in Coupler.io. Use this to discover available templates, optionally filtered by a specific source, metric or category, provide the link to set up the template and provide insights about their contents.

Run a Coupler.io dataflow to refresh its data. This triggers the dataflow to run and fetch the latest data from the source. The dataflowId parameter is optional — the system may resolve it automatically. Do not ask the user for a dataflowId. If the dataflow cannot be resolved, the tool will return an error.

Update the AI context (markdown description) for a dataset. Use this to persist what you learned about the dataset contents so it can be recalled in future sessions. Pass null to clear.